Publications

For the most up-to-date and complete list of publications, please visit my Google Scholar profile.

ViDove: A Translation Agent System with Multimodal Context and Memory-Augmented Reasoning

Yichen Lu*, Wei Dai*, Jiaen Liu*, et al.

EMNLP 2025 System Demonstrations

[Paper] [Code]

GALAXY: A Large-Scale Open-Domain Dataset for Multimodal Learning

Yihan Wu, Yichen Lu, Yijing Chen, Jiaqi Song, William Chen, Ruihua Song, Shinji Watanabe

Interspeech 2025

[Paper]

Enhancing Audiovisual Speech Recognition by Bifocal Preference Optimization

Yihan Wu, Yichen Lu, Y Peng, X Wang, R Song, Shinji Watanabe

AAAI 2025

[Paper]

FastAdaSP: Multitask-Adapted Efficient Inference for Large Speech Language Model

Yichen Lu*, J Song*, CH Yang, Shinji Watanabe

EMNLP 2024 (Oral Presentation)

[Paper] [Code]

SynesLM: A Unified Approach for Audio-visual Speech Recognition and Translation

Yichen Lu*, J Song*, X Chang, H Bian, S Maiti, Shinji Watanabe

Interspeech 2024 Workshop

[Paper]

Robust Audiovisual Speech Recognition Model with Mixture-of-Experts

Yihan Wu, Yifan Peng, Yichen Lu, X Chang, R Song, Shinji Watanabe

SLT 2024

[Paper]

Exploring Speech Recognition, Translation, and Understanding with Discrete Input

Xuankai Chang, B Yan, K Choi, J Jung, Yichen Lu, et al.

ICASSP 2024

[Paper]

Speech-DRAME: A Framework for Human-Aligned Benchmarks in Speech Role-Play

Jiatong Shi, Jionghao Han, Yichen Lu*, et al.

Under Review

[Paper]

Noisy Positive-Unlabeled Learning with Self-Training for Knowledge Graph Completion

Ruijie Wang, B Li, Yichen Lu, D Sun, J Li, Yuchen Yan, S Liu, H Tong, T F. Abdelzaher

ACL 2023 Findings

[Paper]